... models are taken to compute the joint relation between the between the computed and the observed data. In contrast, a porosity, shale content, velocity and resistivity of the strata. neural network model trained on an acceptable range of The velocity and resistivity models thus generated were...

... models when applied to synthetic MT data. upstream oil & gas resistivity model deterministic inversion artificial intelligence applied geoscience exploration geophysicist 10 machine learning objective function iteration neural network training data application algorithm standard...

... machine learning artificial intelligence applied geoscience drilling data acquisition upstream oil & gas reservoir characterization logging while drilling attenuation curve resistivity model geophysics dielectric constant strike direction simultaneous inversion dielectric effect...

... the change in the recovered delineate boundaries (e.g., Dosso and Oldenburg, 1989; resistivity model with the threshold parameter as a means to Farquharson and Oldenburg, 1998). To avoid the numerical delineate the significant boundaries in the subsurface. The difficulties associated with the direct...

... bodies (Colombo et al. 2018). Regarding ML incorporate these distinct data types and tested to assess approaches, Colombo et al. (2020) applied a modified U-Net which best improved the prediction accuracy compared to to map cross-well EM data to resistivity models. Oh et al. either seismic...

... of input-output pairs to make a prediction of a pair of corresponding 2D resistivity models in (X,Y) and (X,Z) orientations. To train the deep learning algorithm, we construct a library of over 15,000 unique synthetic resistivity models and corresponding datasets, varying features such as depth, size...

... on a resistivity model obtained using TDM acquisition (Türko lu et al. 2018). Figure 2 shows the Multi-physics interpretation, based on seismic refraction synthetic resistivity model characterized by a high-resistive sand layer and a less resistive anomaly in the middle. tomography, transient electromagnetic (TEM...

... prior An important hydrogeologic question posed by the local models (e.g. range of average resistivity, resistivity logs), water agency in Butte and Glenn counties was: what is the and six resistivity models were obtained. To better capture vertical connectivity within the aquifer system...

... of DC data separately, and ity of interpreting geophysical data for a broader community. then together to generate a common resistivity model. The data acquisition was curved which might cause artefacts in a 2D in- Our open-source development is motivated by our 2020 Geo- version. To investigate this we...

... The conventional interpretation of airborne electromagnetic (AEM) data has been conducted by solving the inverse problem. With the recent advance in machine learning (ML) techniques, a one-dimensional (1D) deep neural network (DNN) inversion scheme which predicts a 1D resistivity model using...

... upstream oil & gas reservoir characterization machine learning reservoir monitoring assemblage mcneice resolution csem waterflood annual international conference application inversion resistivity model seg international exposition electrode artificial intelligence Tietze , K...

... seismic data was applied as the constraint. To combine the seismic constraint with CSEM data, the modified UNet was adopted as an inversion operator based on DL. For training the DL model based on the network, resistivity models, including a salt body with arbitrary shape and size, and the corresponding...

... ABSTRACT Large scale controlled-source electromagnetic (CSEM) inversion is commonly formulated as a least-square optimization problem using a local gradient-based optimization method, which iteratively updates a starting resistivity model until the misfit between observed and synthetic data...

... ABSTRACT Geological interpretation of 3D resistivity models from marine controlled-source electromagnetic (CSEM) and magnetotelluric (MT) data inversion faces difficulties in the emerging new frontiers for hydrocarbon exploration where structural complexity and anisotropic or low-resistivity...

... ABSTRACT Magnetotelluric inversion algorithms have become an essential tool in exploration geophysics by providing us with resistivity models of the subsurface. Many efforts have been devoted to developing inversion algorithms that can incorporate geological structural information, physical...

... annual international meeting artificial intelligence skip connection contraction path inversion information em inversion saturation em response resistivity model reconstruction neural network variation deep learning resistivity resolution upstream oil & gas machine learning Deep...

... decay gate resolution surface correction seg international exposition joint inversion colombo annual meeting upstream oil & gas resistivity inversion sand dune imaging sand dune resistivity model Auken , E. , A. V. Christiansen , J. Westergaard , C...

... similarity between jointly inverted density and resistivity models using either a direct correlation of the model parameters or a correlation of the gradients of the models. We demonstrate the effectiveness of the developed method and algorithm with two synthetic model studies and a case study of the joint...

... & gas artificial intelligence fermi distribution model estimation marine csem data rune mittet variation final model start model reservoir characterization resistivity model annual meeting inversion Mittet , R. , 2015 , Seismic wave propagation concepts applied...

..., which does not require calculation of sensitivities and provides quantification of the uncertainties in the resistivity model. We apply the inversion methodology to synthetic geothermal test cases where three prior models for the geothermal reservoir were used: one small in size, but with the correct...